
How Data Scientists Work Together With Domain Experts in Scientific Collaborations: To Find The Right Answer Or To Ask The Right Question?
In recent years there has been an increasing trend in which data scienti...
read it

AutoML using Metadata Language Embeddings
As a human choosing a supervised learning algorithm, it is natural to be...
read it

Invertible Gaussian Reparameterization: Revisiting the GumbelSoftmax
The GumbelSoftmax is a continuous distribution over the simplex that is...
read it

One Man's Trash is Another Man's Treasure: Resisting Adversarial Examples by Adversarial Examples
Modern image classification systems are often built on deep neural netwo...
read it

FaceShapeGene: A Disentangled Shape Representation for Flexible Face Image Editing
Existing methods for face image manipulation generally focus on editing ...
read it

ThemeMatters: Fashion Compatibility Learning via Theme Attention
Fashion compatibility learning is important to many fashion markets such...
read it

Noise2Blur: Online Noise Extraction and Denoising
We propose a new framework called Noise2Blur (N2B) for training robust i...
read it

Bidirectional Inference Networks: A Class of Deep Bayesian Networks for Health Profiling
We consider the problem of inferring the values of an arbitrary set of v...
read it

Unrestricted Adversarial Attacks for Semantic Segmentation
Semantic segmentation is one of the most impactful applications of machi...
read it

Stacked SemanticGuided Network for ZeroShot SketchBased Image Retrieval
Zeroshot sketchbased image retrieval (ZSSBIR) is a task of crossdoma...
read it

Learning Your Way Without Map or Compass: Panoramic Target Driven Visual Navigation
We present a robot navigation system that uses an imitation learning fra...
read it

Learning to Compose Dynamic Tree Structures for Visual Contexts
We propose to compose dynamic tree structures that place the objects in ...
read it

Weakly Supervised Attention Networks for FineGrained Opinion Mining and Public Health
In many review classification applications, a finegrained analysis of t...
read it

Zero Shot Learning on Simulated Robots
In this work we present a method for leveraging data from one source to ...
read it

Controversial stimuli: pitting neural networks against each other as models of human recognition
Distinct scientific theories can make similar predictions. To adjudicate...
read it

Practical Deep Reinforcement Learning Approach for Stock Trading
Stock trading strategy plays a crucial role in investment companies. How...
read it

TGAN: Deep Tensor Generative Adversarial Nets for Large Image Generation
Deep generative models have been successfully applied to many applicatio...
read it

Unsupervised Deep Tracking
We propose an unsupervised visual tracking method in this paper. Differe...
read it

ESMAML: Simple HessianFree Meta Learning
We introduce ESMAML, a new framework for solving the model agnostic met...
read it

PointHop: An Explainable Machine Learning Method for Point Cloud Classification
An explainable machine learning method for point cloud classification, c...
read it

MultiTask Gaussian Processes and Dilated Convolutional Networks for Reconstruction of Reproductive Hormonal Dynamics
We present an endtoend statistical framework for personalized, accurat...
read it

Rethinking Generative Coverage: A Pointwise Guaranteed Approach
All generative models have to combat missing modes. The conventional wis...
read it

Individual predictions matter: Assessing the effect of data ordering in training finetuned CNNs for medical imaging
We reproduced the results of CheXNet with fixed hyperparameters and 50 d...
read it

Adaptive SampleEfficient Blackbox Optimization via ESactive Subspaces
We present a new algorithm ASEBO for conducting optimization of highdim...
read it

General Partial Label Learning via Dual Bipartite Graph Autoencoder
We formulate a practical yet challenging problem: General Partial Label ...
read it

Hierarchical Long ShortTerm Concurrent Memory for Human Interaction Recognition
In this paper, we aim to address the problem of human interaction recogn...
read it

Moment Matching for MultiSource Domain Adaptation
Conventional unsupervised domain adaptation (UDA) assumes that training ...
read it

FullyFeatured Attribute Transfer
Image attribute transfer aims to change an input image to a target one w...
read it

Segmentation with Residual Attention UNet and an EdgeEnhancement Approach Preserves Cell Shape Features
The ability to extrapolate gene expression dynamics in living single cel...
read it

TreeStructured Recurrent Switching Linear Dynamical Systems for MultiScale Modeling
Many realworld systems studied are governed by complex, nonlinear dynam...
read it

Deep Reinforcement Learning for Intelligent Transportation Systems
Intelligent Transportation Systems (ITSs) are envisioned to play a criti...
read it

Bayesian Tensor Filtering: Smooth, LocallyAdaptive Factorization of Functional Matrices
We consider the problem of functional matrix factorization, finding low...
read it

SemEval2015 Task 10: Sentiment Analysis in Twitter
In this paper, we describe the 2015 iteration of the SemEval shared task...
read it

Structured Monte Carlo Sampling for Nonisotropic Distributions via Determinantal Point Processes
We propose a new class of structured methods for Monte Carlo (MC) sampli...
read it

Image Outpainting and Harmonization using Generative Adversarial Networks
Although the inherently ambiguous task of predicting what resides beyond...
read it

(Sequential) Importance Sampling Bandits
The multiarmed bandit (MAB) problem is a sequential allocation task whe...
read it

Multilevel Multimodal Common Semantic Space for ImagePhrase Grounding
We address the problem of phrase grounding by learning a multilevel com...
read it

Hierarchical Macro Strategy Model for MOBA Game AI
The next challenge of game AI lies in Real Time Strategy (RTS) games. RT...
read it

PixelAttentive Policy Gradient for MultiFingered Grasping in Cluttered Scenes
Recent advances in onpolicy reinforcement learning (RL) methods enabled...
read it

Two models of double descent for weak features
The "double descent" risk curve was recently proposed to qualitatively d...
read it

How many variables should be entered in a principal component regression equation?
We study least squares linear regression over N uncorrelated Gaussian fe...
read it

Leveraging Just a Few Keywords for FineGrained Aspect Detection Through Weakly Supervised CoTraining
Usergenerated reviews can be decomposed into finegrained segments (e.g...
read it

Substituting Gadolinium in Brain MRI Using DeepContrast
Cerebral blood volume (CBV) is a hemodynamic correlate of oxygen metabol...
read it

Ensemble Model Patching: A ParameterEfficient Variational Bayesian Neural Network
Two main obstacles preventing the widespread adoption of variational Bay...
read it

A New Distribution on the Simplex with AutoEncoding Applications
We construct a new distribution for the simplex using the Kumaraswamy di...
read it

Reinforcement Learning with Chromatic Networks
We present a new algorithm for finding compact neural networks encoding ...
read it

The continuous Bernoulli: fixing a pervasive error in variational autoencoders
Variational autoencoders (VAE) have quickly become a central tool in mac...
read it

Video Relocalization
Many methods have been developed to help people find the video contents ...
read it

Boosting Trust Region Policy Optimization by Normalizing Flows Policy
We propose to improve trust region policy search with normalizing flows ...
read it

Agent Embeddings: A Latent Representation for PoleBalancing Networks
We show that it is possible to reduce a highdimensional object like a n...
read it
Columbia University
Located In New York City, The School at Columbia University is a Private K8 Day School serving neighborhood families and Columbia University employees.